bfpill's picture
Checkpoint at 20000 steps
d7c8652
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06,
"eval_steps": 500,
"global_step": 1200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0025,
"grad_norm": 1.0703125,
"learning_rate": 0.00025,
"loss": 10.4938,
"step": 50
},
{
"epoch": 0.005,
"grad_norm": 0.90625,
"learning_rate": 0.0005,
"loss": 9.1324,
"step": 100
},
{
"epoch": 0.0075,
"grad_norm": 0.62890625,
"learning_rate": 0.00075,
"loss": 7.883,
"step": 150
},
{
"epoch": 0.01,
"grad_norm": 0.42578125,
"learning_rate": 0.001,
"loss": 7.3925,
"step": 200
},
{
"epoch": 0.0125,
"grad_norm": 0.6171875,
"learning_rate": 0.0009999842657116666,
"loss": 7.062,
"step": 250
},
{
"epoch": 0.015,
"grad_norm": 0.498046875,
"learning_rate": 0.0009999370638369377,
"loss": 6.8396,
"step": 300
},
{
"epoch": 0.0175,
"grad_norm": 0.4296875,
"learning_rate": 0.0009998583973465647,
"loss": 6.6879,
"step": 350
},
{
"epoch": 0.02,
"grad_norm": 0.435546875,
"learning_rate": 0.0009997482711915926,
"loss": 6.6086,
"step": 400
},
{
"epoch": 0.0225,
"grad_norm": 0.63671875,
"learning_rate": 0.0009996066923030483,
"loss": 6.5239,
"step": 450
},
{
"epoch": 0.025,
"grad_norm": 0.37109375,
"learning_rate": 0.000999433669591504,
"loss": 6.552,
"step": 500
},
{
"epoch": 0.0275,
"grad_norm": 0.5234375,
"learning_rate": 0.0009992292139465165,
"loss": 6.4607,
"step": 550
},
{
"epoch": 0.03,
"grad_norm": 0.61328125,
"learning_rate": 0.0009989933382359422,
"loss": 6.3974,
"step": 600
},
{
"epoch": 0.0325,
"grad_norm": 0.67578125,
"learning_rate": 0.0009987260573051267,
"loss": 6.3249,
"step": 650
},
{
"epoch": 0.035,
"grad_norm": 0.51953125,
"learning_rate": 0.0009984273879759713,
"loss": 6.3374,
"step": 700
},
{
"epoch": 0.0375,
"grad_norm": 0.482421875,
"learning_rate": 0.0009980973490458728,
"loss": 6.3157,
"step": 750
},
{
"epoch": 0.04,
"grad_norm": 0.55859375,
"learning_rate": 0.0009977359612865424,
"loss": 6.2525,
"step": 800
},
{
"epoch": 0.0425,
"grad_norm": 0.53125,
"learning_rate": 0.0009973432474426967,
"loss": 6.2116,
"step": 850
},
{
"epoch": 0.045,
"grad_norm": 0.439453125,
"learning_rate": 0.000996919232230627,
"loss": 6.1993,
"step": 900
},
{
"epoch": 0.0475,
"grad_norm": 0.384765625,
"learning_rate": 0.0009964639423366442,
"loss": 6.0863,
"step": 950
},
{
"epoch": 0.05,
"grad_norm": 0.349609375,
"learning_rate": 0.0009959774064153978,
"loss": 6.049,
"step": 1000
},
{
"epoch": 0.0525,
"grad_norm": 0.44140625,
"learning_rate": 0.0009954596550880734,
"loss": 6.0222,
"step": 1050
},
{
"epoch": 0.055,
"grad_norm": 0.453125,
"learning_rate": 0.0009949107209404665,
"loss": 6.0078,
"step": 1100
},
{
"epoch": 0.0575,
"grad_norm": 0.494140625,
"learning_rate": 0.000994330638520929,
"loss": 6.0114,
"step": 1150
},
{
"epoch": 0.06,
"grad_norm": 0.46484375,
"learning_rate": 0.0009937194443381972,
"loss": 5.9764,
"step": 1200
}
],
"logging_steps": 50,
"max_steps": 20000,
"num_input_tokens_seen": 0,
"num_train_epochs": 9223372036854775807,
"save_steps": 100,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1745535841075200.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}